@inproceedings{fu-etal-2026-ci,
    title = "{CI}-Work: Benchmarking Contextual Integrity in Enterprise {LLM} Agents",
    author = "Fu, Wenjie  and
      Qin, Xiaoting  and
      Zhang, Jue  and
      Lin, Qingwei  and
      Wutschitz, Lukas  and
      Sim, Robert  and
      Rajmohan, Saravan  and
      Zhang, Dongmei",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.103/",
    pages = "1483--1508",
    ISBN = "979-8-89176-394-4",
    abstract = "Enterprise LLM agents can dramatically improve workplace productivity, but their core capability, retrieving and using internal context to act on a user{'}s behalf, also creates new risks for sensitive information leakage. We introduce **CI-Work**, a Contextual Integrity (CI)-grounded benchmark that simulates enterprise workflows across five information-flow directions and evaluates whether agents can convey *essential* content while withholding *sensitive* context in dense retrieval settings.Our evaluation of frontier models reveals that privacy failures are prevalent (violation rates range from 15.8{\%}-50.9{\%}, with leakage reaching up to 26.7{\%}) and uncovers a counterintuitive trade-off critical for industrial deployment: higher task utility often correlates with increased privacy violations.Moreover, the massive scale of enterprise data and potential user behavior further amplify this vulnerability. Simply increasing model size or reasoning depth fails to address the problem. We conclude that safeguarding enterprise workflows requires a paradigm shift, moving beyond model-centric scaling toward context-centric architectures."
}